Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2623f5b52f366a3149ee5f94a2de76936d72603531cb4c40f79a5425c0f7e3
+oid sha256:a22f9375dd7f4f0ada7b41a4e0c78592fc31ad9f3bacce41636af8643d7395a5
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:021b91241b0c0f56423e62e108eeef830a824e1a9313356165bd179a9c2565ed
+oid sha256:785bb480d8e758e7ca847ed3cf975951a5215aa290ce424fb810109f53a378f5
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab989b5295c746dcc55eaca6e59d79f6a15092bf1224b6d8e264e14d5da2f349
+oid sha256:51e8b2fc4db8f9f1f3915da8648aba6d1347f93115d434a4ee43666e96ce20d3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a607ed79cb269189f22c668c589dcb86edfee8d3b8e6e8f18f56d7b6c0bde4e0
+oid sha256:c4a7013ad699cdbd4687a756cbad637840e40c643633e099b2497c48ddd51991
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cfca1cac7bbc8c0cecb55c7d8fa90d506d4709a85fea20ae83a2c97b37fd05
+oid sha256:cbe087001ac59180b30fc69f929ec546dcc1895cfc4d8518c778ea09ec927593
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd13f61ea63b8017dab1ff3e53c8de6e05ab465613b2270323d3fd23586735de
+oid sha256:d45c824ce51fffe47243f6a0bbbd0e5eaaba0d1d8d2a133c6bc84dcbd00f3acf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4251263737678528,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.217910447761194,
+  "best_metric": 0.4023851752281189,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.435820895522388,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 86.336,
       "eval_steps_per_second": 11.022,
       "step": 25
+    },
+    {
+      "epoch": 1.2656716417910447,
+      "grad_norm": 0.18197745084762573,
+      "learning_rate": 5e-05,
+      "loss": 0.378,
+      "step": 26
+    },
+    {
+      "epoch": 1.3134328358208955,
+      "grad_norm": 0.1775834709405899,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4182,
+      "step": 27
+    },
+    {
+      "epoch": 1.3611940298507463,
+      "grad_norm": 0.19821526110172272,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4157,
+      "step": 28
+    },
+    {
+      "epoch": 1.408955223880597,
+      "grad_norm": 0.21566687524318695,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3821,
+      "step": 29
+    },
+    {
+      "epoch": 1.4567164179104477,
+      "grad_norm": 0.2709551453590393,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3742,
+      "step": 30
+    },
+    {
+      "epoch": 1.5044776119402985,
+      "grad_norm": 0.1894427090883255,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.372,
+      "step": 31
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 0.19189490377902985,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4192,
+      "step": 32
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.22904697060585022,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4083,
+      "step": 33
+    },
+    {
+      "epoch": 1.6477611940298509,
+      "grad_norm": 0.24419617652893066,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4,
+      "step": 34
+    },
+    {
+      "epoch": 1.6955223880597015,
+      "grad_norm": 0.250863641500473,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3735,
+      "step": 35
+    },
+    {
+      "epoch": 1.7432835820895523,
+      "grad_norm": 0.22108954191207886,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3983,
+      "step": 36
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.1873919814825058,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3949,
+      "step": 37
+    },
+    {
+      "epoch": 1.8388059701492536,
+      "grad_norm": 0.2162359058856964,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4166,
+      "step": 38
+    },
+    {
+      "epoch": 1.8865671641791044,
+      "grad_norm": 0.2337595373392105,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.377,
+      "step": 39
+    },
+    {
+      "epoch": 1.9343283582089552,
+      "grad_norm": 0.2757619619369507,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3678,
+      "step": 40
+    },
+    {
+      "epoch": 2.005970149253731,
+      "grad_norm": 0.30736440420150757,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5346,
+      "step": 41
+    },
+    {
+      "epoch": 2.053731343283582,
+      "grad_norm": 0.17773054540157318,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3897,
+      "step": 42
+    },
+    {
+      "epoch": 2.1014925373134328,
+      "grad_norm": 0.18972079455852509,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3795,
+      "step": 43
+    },
+    {
+      "epoch": 2.1492537313432836,
+      "grad_norm": 0.21727779507637024,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3802,
+      "step": 44
+    },
+    {
+      "epoch": 2.1970149253731344,
+      "grad_norm": 0.25702959299087524,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3841,
+      "step": 45
+    },
+    {
+      "epoch": 2.244776119402985,
+      "grad_norm": 0.26603198051452637,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3291,
+      "step": 46
+    },
+    {
+      "epoch": 2.292537313432836,
+      "grad_norm": 0.1831669956445694,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4069,
+      "step": 47
+    },
+    {
+      "epoch": 2.3402985074626868,
+      "grad_norm": 0.20122045278549194,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3851,
+      "step": 48
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 0.2129780352115631,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3787,
+      "step": 49
+    },
+    {
+      "epoch": 2.435820895522388,
+      "grad_norm": 0.2397255003452301,
+      "learning_rate": 0.0,
+      "loss": 0.3508,
+      "step": 50
+    },
+    {
+      "epoch": 2.435820895522388,
+      "eval_loss": 0.4023851752281189,
+      "eval_runtime": 1.632,
+      "eval_samples_per_second": 86.399,
+      "eval_steps_per_second": 11.03,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null